© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146270
    Prev
    Next
    INDEX
    Explanations

    common continuations

    np_acts-logits-general · gemini-2.5-flash-lite

    data structures and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     열심히
    0.48
    ៅ
    0.45
     менедж
    0.45
     Суриков
    0.44
     벗
    0.44
     인식
    0.44
    мо
    0.44
     равномер
    0.44
    
    0.44
    기에
    0.43
    POSITIVE LOGITS
    in
    0.50
     Hereford
    0.50
     begon
    0.43
     கதா
    0.43
    ro
    0.43
     নিষেধ
    0.43
    novae
    0.42
     Pferde
    0.42
    horse
    0.42
    ceans
    0.42
    Activations Density 0.000%

    No Known Activations